Verifiable AI: Enhancing FATE with Provenance Intelligence
DOI:
https://doi.org/10.15680/IJCTECE.2021.0403001Keywords:
Verifiable AI, Provenance Intelligence, FATE (Fairness, Accountability, Transparency, Explainability), Explainable AI (XAI), Trustworthy AI (TAI), Data Provenance, Generative AI, Zero-Knowledge Proofs IAbstract
This paper explores the integration of Provenance Intelligence into the FATE (Fairness, Accountability, Transparency, and Explainability) framework to enhance the verifiability of AI systems. Provenance Intelligence involves tracking and documenting the origins, transformations, and usage of data throughout the AI lifecycle. By embedding provenance information, AI systems can provide clearer insights into decision-making processes, identify and mitigate biases, ensure accountability, and foster user trust. This approach aligns with emerging standards and tools that aim to combat misinformation, ensure data integrity, and uphold ethical AI practices.
References
1. Kale, A., Nguyen, T., Harris, F. C., Li, C., Zhang, J., & Ma, X. Provenance documentation to enable explainable and trustworthy AI: A literature review. Data Intelligence, 5(1), 139–162. [DOI:10.1162/dint_a_00119]
2. Saxena, R., & Bharti, D. (2025). Establishing data provenance for responsible artificial intelligence systems. ACM Transactions on Management Information Systems. [DOI:10.1145/3503488]
3. Tang, N., Yang, C., Fan, J., Cao, L., & Zhang, J. (2023). VerifAI: Verifying generative AI outputs through provenance analysis. arXiv preprint arXiv:2307.02796.
4. Singh, J., Cobbe, J., & Norval, C. (. Decision provenance: Harnessing data flow for accountable systems. arXiv preprint arXiv:1804.05741.
5. Vilone, G., & Longo, L. Explainable Artificial Intelligence: A systematic review. arXiv preprint arXiv:2006.00093.
6. Mersha, M., Lam, K., Wood, J., AlShami, A., & Kalita, J. (2024). Explainable Artificial Intelligence: A survey of needs, techniques, applications, and future directions. arXiv preprint arXiv:2409.00265.
7. Gunning, D. ARPA's explainable artificial intelligence (XAI) program. Proceedings of the 24th International Conference on Intelligent User Interfaces, 44–58.
8. Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., & Herrera, F. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82–115. [DOI:10.1016/j.inffus.2019.12.012]
9. Holzinger, A., Biemann, C., Pattichis, C. S., & Kell, D. B.What do we need to build explainable AI systems for the medical domain? arXiv preprint arXiv:1712.09923.
10. Belle, V., & PapantonisPrinciples and practice of explainable machine learning. Frontiers in Big Data, 4, 25. [DOI:10.3389/fdata.2021.688969]
11. Lebo, T., Moreau, L., & Groth, P. (2013). PROV-O: The PROV Ontology. W3C Recommendation. [W3C: http://www.w3.org/TR/2013/REC-prov-o-20130430/]
12. Huynh, T. D., & Moreau, L. ProvStore: A public provenance repository. Proceedings of the 2014 International Provenance and Annotation Workshop, 275–277. [DOI:10.1145/2661433.2661453]
13. Moreau, L., & Huynh, T. DAn online validator for provenance: Algorithmic design, testing, and API. Proceedings of the International Conference on Fundamental Approaches to Software Engineering, 291–305.
[DOI:10.1007/978-3-642-54805-8_21]
14. Kohwalter, T., & Moreau, L.ProvViewer: A graph-based visualization tool for interactive exploration of
provenance data. Proceedings of the International Provenance and Annotation Workshop, 71–82. [DOI:10.1145/3007748.3007750]
15. Amstutz, P., et al. (2016). Common Workflow Language, V1.0. Figshare. [DOI:10.6084/m9.figshare.3115156.v2]
16. Vanschoren, J., et alOpenML: Networked science in machine learning. ACM SIGKDD Explorations Newsletter, 15(2), 49–60. [DOI:10.1145/2685289.2685290]
17. Vartak, M., et al. ModelDB: A system for machine learning model management. Proceedings of the Workshop on Human-In-the-Loop Data Analytics, 1–3. [DOI:10.1145/3001960.3001961]
18. Simmhan, Y. L., Plale, B., & Gannon, DA survey of data provenance in e-science. ACM SIGMOD Record, 34(3),31–36. [DOI:10.1145/1084805.1084809]
19. Buneman, P., Khanna, S., & Tan, W. C. Curated databases. Proceedings of the 27th ACM SIGMOD-SIGACTSIGART Symposium on Principlesof Database Systems, 1–12. [DOI:10.1145/1376606.1376607]
